{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:73HLCZQH2R4YJUI65FZS6N2BJD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c7a0c1a710cf54b9f155911d0418217b750f34038da55b84b1c48a7952e05b53","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-14T01:16:32Z","title_canon_sha256":"34a99622bdb790e6af3bed05106d949d74f17d9f0212533ee50aa22ae5baa52d"},"schema_version":"1.0","source":{"id":"2405.12983","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12983","created_at":"2026-07-05T08:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12983v1","created_at":"2026-07-05T08:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12983","created_at":"2026-07-05T08:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"73HLCZQH2R4Y","created_at":"2026-07-05T08:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"73HLCZQH2R4YJUI6","created_at":"2026-07-05T08:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"73HLCZQH","created_at":"2026-07-05T08:22:23Z"}],"graph_snapshots":[{"event_id":"sha256:2b1522fc21ea6a93b06d13e7f82b8cee8498a15a9ad2e3be7251e50c45ee7fb0","target":"graph","created_at":"2026-07-05T08:22:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.12983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans are adept at leveraging visual cues from lip movements for recognizing speech in adverse listening conditions. Audio-Visual Speech Recognition (AVSR) models follow similar approach to achieve robust speech recognition in noisy conditions. In this work, we present a multilingual AVSR model incorporating several enhancements to improve performance and audio noise robustness. Notably, we adapt the recently proposed Fast Conformer model to process both audio and visual modalities using a novel hybrid CTC/RNN-T architecture. We increase the amount of audio-visual training data for six distin","authors_text":"Boris Ginsburg, Jagadeesh Balam, Krishna C. Puvvada, Maxime Burchi, Radu Timofte","cross_cats":["cs.AI","cs.CV","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-14T01:16:32Z","title":"Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12983","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7111508d788bd470a598af11597c767d1c6bc94d2d6a1faf4dd6e7c751caf9c4","target":"record","created_at":"2026-07-05T08:22:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c7a0c1a710cf54b9f155911d0418217b750f34038da55b84b1c48a7952e05b53","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-14T01:16:32Z","title_canon_sha256":"34a99622bdb790e6af3bed05106d949d74f17d9f0212533ee50aa22ae5baa52d"},"schema_version":"1.0","source":{"id":"2405.12983","kind":"arxiv","version":1}},"canonical_sha256":"feceb16607d47984d11ee9732f374148e1230a48a4e3a94e9ad4ee26a1ba283e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"feceb16607d47984d11ee9732f374148e1230a48a4e3a94e9ad4ee26a1ba283e","first_computed_at":"2026-07-05T08:22:23.345416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:23.345416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DJvEGCMaMfRx4FN/azlFU4+p4yz76cNxWRMIkPDaEM2IDCUNVOl3HUmsMUAr10t7pWZonrRAeJUIPJ9KG3xIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:23.345914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12983","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7111508d788bd470a598af11597c767d1c6bc94d2d6a1faf4dd6e7c751caf9c4","sha256:2b1522fc21ea6a93b06d13e7f82b8cee8498a15a9ad2e3be7251e50c45ee7fb0"],"state_sha256":"ec0976500ea9b1ab2f63fc3ac1989f2a1cdec4d747e1cfbd38809c705459716f"}